Learning Task Sampling Policy for Multitask Learning

Dhanasekar Sundararaman*, Henry Tsai, Kuang Huei Lee, Iulia Turc, Lawrence Carin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

It has been shown that training multi-task models with auxiliary tasks can improve the target tasks quality through cross-task transfer. However, the importance of each auxiliary task to the primary task is likely not known a priori. While the importance weights of auxiliary tasks can be manually tuned, it becomes practically infeasible with the number of tasks scaling up. To address this, we propose a search method that automatically assigns importance weights. We formulate it as a reinforcement learning problem and learn a task sampling schedule based on evaluation accuracy of the multi-task model. Our empirical evaluation on XNLI and GLUE shows that our method outperforms uniform sampling and the corresponding single-task baseline.

Original languageEnglish (US)
Title of host publicationFindings of the Association for Computational Linguistics, Findings of ACL
Subtitle of host publicationEMNLP 2021
EditorsMarie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-Tau Yih
PublisherAssociation for Computational Linguistics (ACL)
Pages4410-4415
Number of pages6
ISBN (Electronic)9781955917100
StatePublished - 2021
Event2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021 - Punta Cana, Dominican Republic
Duration: Nov 7 2021Nov 11 2021

Publication series

NameFindings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021

Conference

Conference2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
Country/TerritoryDominican Republic
CityPunta Cana
Period11/7/2111/11/21

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Learning Task Sampling Policy for Multitask Learning'. Together they form a unique fingerprint.

Cite this